Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8906
    Prev
    Next
    INDEX
    Explanations

    quoted speech or dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    end quote or apostrophe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.75
     snippetHide
    -0.71
    bootstrapcdn
    -0.68
     JpaRepository
    -0.67
     BoxFit
    -0.65
     müſſen
    -0.64
     queſta
    -0.64
    DockStyle
    -0.63
     sumpay
    -0.62
    ſammen
    -0.60
    POSITIVE LOGITS
    “
    1.10
     "
    0.95
     “
    0.87
    "
    0.87
    ("
    0.85
     '
    0.78
    ="
    0.71
    (“
    0.69
    ('
    0.69
    ‘
    0.65
    Activations Density 0.023%

    No Known Activations